Abstract: Systems, methods, and techniques are provided for a fabric addressable memory. A memory access request is received from a host computing device attached via one edge port of one or more interconnect switches, the memory access request directed to a destination segment of a physical fabric memory block that is allocated in local physical memory of the host computing device. The edge port accesses a stored mapping between segments of the physical fabric memory block and one or more destination port identifiers that are each associated with a respective edge port of the fabric addressable memory. The memory access request is routed by the one edge port to a destination edge port based on the stored mapping.

Abstract: Devices, systems, and methods for sampling partially resident texture data. An instruction which includes a residency map descriptor is received. The instruction is executed to retrieve partially resident texture data from a mipmap stored in a memory based on the residency map descriptor. The residency map descriptor includes a residency map.

Abstract: A computing system may implement a method for creating a first subdomain by configuring one of a first plurality of slave nodes as a first subdomain master node and configuring one or more other slave nodes of the first plurality of slave nodes as first subdomain slave nodes to the first subdomain master node.

Abstract: A memory controller includes an arbiter, a vector arithmetic logic unit (VALU), a read buffer and a write buffer both coupled to the VALU, and an atomic memory operation scheduler. The VALU performs scattered atomic memory operations on arrays of data elements responsive to selected memory access commands. The atomic memory operation scheduler is for scheduling atomic memory operations at the VALU; identifying a plurality of scattered atomic memory operations with commutative and associative properties, the plurality of scattered atomic memory operations on at least one element of an array of data elements associated with an address; and commanding the VALU to perform the plurality of scattered atomic memory operations.

Abstract: One or both of read and write accesses to a fabric-attached memory module via a fabric interconnect are monitored. In one or more implementations, offloading of one or more tasks accessing the fabric-attached memory module to a processor of a routing system associated with the fabric-attached memory module is initiated based on the read and write accesses to the fabric-attached memory module. Additionally or alternatively, replicating memory of the fabric-attached memory module to a cache memory of a computing node in the disaggregated memory system executing one or more tasks of a host application is initiated based on the write accesses to the fabric-attached memory module.

Abstract: A method for die pair partitioning can include providing a circuit die. The method can additionally include providing one or more additional circuit die having one or more fuses positioned therein, wherein the one or more fuses identify the circuit die. The method can also include connecting the one or more additional circuit die to the circuit die. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A method for circuit die stacking can include providing a first circuit die having a first metal stack, wherein the first circuit die corresponds to a primary thermal source of an integrated circuit including the first circuit die. The method can additionally include providing a second circuit die of the integrated circuit, wherein the second circuit die has a second metal stack and is configured for connection to at least one of a package substrate or an additional die. The method can also include connecting the first metal stack to the second metal stack. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A method for die pair partitioning can include providing a circuit die that has a metal stack and that includes a majority of logic transistors of an integrated circuit. The method can also include providing one or more additional circuit die that have one or more additional metal stacks of which at least one is connected to the metal stack of the circuit die and a majority of static random access memory and analog devices of the integrated circuit. The method can further include connecting at least one of the one or more additional metal stacks to the metal stack of the circuit die. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: One or both of read and write accesses to a fabric-attached memory module via a fabric interconnect are monitored. In one or more implementations, offloading of one or more tasks accessing the fabric-attached memory module to a processor of a routing system associated with the fabric-attached memory module is initiated based on the read and write accesses to the fabric-attached memory module. Additionally or alternatively, replicating memory of the fabric-attached memory module to a cache memory of a computing node in the disaggregated memory system executing one or more tasks of a host application is initiated based on the write accesses to the fabric-attached memory module.

Abstract: A method for implementing shared metal connectivity between 3D stacked circuit dies can include providing a first circuit die having a first metal stack. The method can additionally include providing a second circuit die having a second metal stack, wherein at least one metal layer of the second metal stack is utilized by both the first circuit die and the second circuit die. The method can also include connecting the second metal stack to the first metal stack of the first circuit die. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A method for providing backside power can include providing a first circuit die having a first metal stack. The method can also include connecting a second metal stack of a second circuit die to the first metal stack of the first circuit die, wherein a backside power delivery network is located in a passivation layer of at least one of the first circuit die or the second circuit die. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Duplicating memory content with chipset attached memory is described. In accordance with the described techniques, contents of a system memory are duplicated on a chipset attached memory over a chipset link. Memory requests are serviced using the contents of the system memory and the contents on the chipset attached memory. Servicing the memory requests includes servicing a first portion of a read request using the contents of the system memory and a second, remaining portion of the read request using the contents on the chipset attached memory. Servicing the memory requests further includes communicating a write request to the system memory and to the chipset attached memory.

Abstract: A method for die pair partitioning can include providing a first circuit die having a first metal stack. The method can additionally include positioning a second circuit die having a second metal stack in a manner that places a temperature sensor in a transistor layer of the second circuit die in planar proximity to at least one hot spot located in an additional transistor layer of the first circuit die. The method can also include connecting the first metal stack of the first circuit die to the second metal stack of the second circuit die. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: An integrated circuit includes a latch array including a plurality of latches logically configured in rows and columns, a plurality of repair latches operatively coupled to the plurality of latches and latch array built in self-test and repair logic (LABISTRL) coupled to the plurality of latches. In some implementations the LABISTRL configures latches in the array as one or more column serial test shift register, detects one or more defective latches of the plurality of latches based on applied test data, and selects at least one repair latch in response to detection of at least one defective latch.

Abstract: A computing system may implement a basic input/output system (BIOS) update method. The BIOS also includes identifying an installed central processing unit (CPU) of a computer system coupled to a BIOS chipset, selecting CPU firmware corresponding to the installed CPU from a plurality of CPU platform firmware stored on a first memory, and loading the CPU firmware into a shared portion of a second memory coupled to the BIOS chipset, where the shared portion of the second memory is configured to store the CPU firmware as secondary CPU firmware.

Abstract: An Address Mapping-Aware Tasking (AMAT) mechanism manages compute task data and issues compute tasks on behalf of threads that created the compute task data. The AMAT mechanism stores compute task data generated by host threads in a set of partitions, where each partition is designated for a particular memory module. The AMAT mechanism maintains address mapping data that maps address information to partitions. Threads push compute task data to the AMAT mechanism instead of generating and issuing their own compute tasks. The AMAT mechanism uses address information included in the compute task data and the address mapping data to determine partitions in which to store the compute task data. The AMAT mechanism then issues compute tasks to be executed near the corresponding memory modules (i.e., in PIM execution units or NUMA compute nodes) based upon the compute task data stored in the partitions.

Abstract: Methods, devices, and systems for information communication. Information transmitted from a host to a graphics processing unit (GPU) is received by information analysis circuitry of a field-programmable gate array (FPGA). A pattern in the information is determined by the information analysis circuitry. A predicted information pattern is determined, by the information analysis circuitry, based on the information. An indication of the predicted information pattern is transmitted to the host. Responsive to a signal from the host based on the predicted information pattern, the FPGA is reprogrammed to implement decompression circuitry based on the predicted information pattern. In some implementations, the information includes a plurality of packets. In some implementations, the predicted information pattern includes a pattern in a plurality of packets. In some implementations, the predicted information pattern includes a zero data pattern.

Abstract: A system and method for efficiently routing scan data between two dies used in three-dimensional packaging are described. In various implementations, a computing system includes at least a first semiconductor die (or first die) and a second die connected to one another within a three-dimensional (3D) package. The first die and the second die have multiple non-scan input/output (I/O) data channels between them for data transfer. The non-scan I/O data channels are partitioned into groups. The first die receives a given scan input data bit for testing a device under test (DUT) on the second die. The first die selects a first group of non-scan I/O data channels, and sends, to the second die, a copy of the given scan input data bit on each non-scan I/O data channel of the first group. The second die uses a voter circuit to determine the value of the given scan input data bit.

Abstract: A method for operating a memory having a plurality of banks accessible in parallel, each bank including a plurality of grains accessible in parallel is provided. The method includes: based on a memory access request that specifies a memory address, identifying a set that stores data for the memory access request, wherein the set is spread across multiple grains of the plurality of grains; and performing operations to satisfy the memory access request, using entries of the set stored across the multiple grains of the plurality of grains.

Abstract: Systems and methods for cache replacement are disclosed. Techniques are described that determine a re-reference interval prediction (RRIP) value of respective data blocks in a cache, where an RRIP value represents a likelihood that a respective data block will be re-used within a time interval. Upon an access, by a processor, to a data segment in a memory, if the data segment is not stored in the cache, a data block in the cache to be replaced by the data segment is selected, utilizing a binary tree that tracks recency of data blocks in the cache.